{"id":"https://openalex.org/W4391733873","doi":"https://doi.org/10.1121/10.0024353","title":"Child-adult speech diarization in naturalistic conditions of preschool classrooms using room-independent ResNet model and automatic speech recognition-based re-segmentation","display_name":"Child-adult speech diarization in naturalistic conditions of preschool classrooms using room-independent ResNet model and automatic speech recognition-based re-segmentation","publication_year":2024,"publication_date":"2024-02-01","ids":{"openalex":"https://openalex.org/W4391733873","doi":"https://doi.org/10.1121/10.0024353","pmid":"https://pubmed.ncbi.nlm.nih.gov/38341746"},"language":"en","primary_location":{"id":"doi:10.1121/10.0024353","doi":"https://doi.org/10.1121/10.0024353","is_oa":false,"landing_page_url":"https://doi.org/10.1121/10.0024353","pdf_url":null,"source":{"id":"https://openalex.org/S11296630","display_name":"The Journal of the Acoustical Society of America","issn_l":"0001-4966","issn":["0001-4966","1520-8524","1520-9024"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","ccf-b","cwts-core","dongbi-b","erih-plus","jufo-3","ki-jl-1","medline","norway-2","poland-100","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310320226","host_organization_name":"Acoustical Society of America","host_organization_lineage":["https://openalex.org/P4310320226"],"host_organization_lineage_names":["Acoustical Society of America"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Journal of the Acoustical Society of America","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017818279","display_name":"Prasanna V. Kothalkar","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Prasanna V. Kothalkar","raw_affiliation_strings":["Center for Robust Speech Systems (CRSS), Erik Jonsson School of Engineering and Computer Science, University of Texas at Dallas 1 , Richardson, Texas 75080, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), Erik Jonsson School of Engineering and Computer Science, University of Texas at Dallas 1 , Richardson, Texas 75080, USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057910370","display_name":"John H. L. Hansen","orcid":"https://orcid.org/0000-0003-1382-9929","observed_orcids":["https://orcid.org/0000-0003-1382-9929"]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John H. L. Hansen","raw_affiliation_strings":["Center for Robust Speech Systems (CRSS), Erik Jonsson School of Engineering and Computer Science, University of Texas at Dallas 1 , Richardson, Texas 75080, USA"],"raw_orcid":"https://orcid.org/0000-0003-1382-9929","affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), Erik Jonsson School of Engineering and Computer Science, University of Texas at Dallas 1 , Richardson, Texas 75080, USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005913278","display_name":"Dwight Irvin","orcid":"https://orcid.org/0000-0002-2324-7124","observed_orcids":["https://orcid.org/0000-0002-2324-7124"]},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dwight Irvin","raw_affiliation_strings":["Anita Zucker Center for Excellence in Early Childhood Studies, University of Florida, Gainesville 2 , Florida 32611, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Anita Zucker Center for Excellence in Early Childhood Studies, University of Florida, Gainesville 2 , Florida 32611, USA","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047277727","display_name":"Jay F. Buzhardt","orcid":"https://orcid.org/0000-0003-4634-3183","observed_orcids":["https://orcid.org/0000-0003-4634-3183"]},"institutions":[{"id":"https://openalex.org/I146416000","display_name":"University of Kansas","ror":"https://ror.org/001tmjg57","country_code":"US","type":"education","lineage":["https://openalex.org/I146416000"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jay Buzhardt","raw_affiliation_strings":["Juniper Garden's Children's Project (JGCP), University of Kansas 3 , Kansas 66101, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Juniper Garden's Children's Project (JGCP), University of Kansas 3 , Kansas 66101, USA","institution_ids":["https://openalex.org/I146416000"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2939,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.52727348,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"155","issue":"2","first_page":"1198","last_page":"1215"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9878000020980835,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9878000020980835,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.007699999958276749,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.002400000113993883,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speaker-diarization","display_name":"speaker diarization","score":0.9070000052452087},{"id":"https://openalex.org/keywords/preschool-classrooms","display_name":"preschool classrooms","score":0.9079999923706055},{"id":"https://openalex.org/keywords/knowledge-distillation","display_name":"knowledge distillation","score":0.7160000205039978},{"id":"https://openalex.org/keywords/resnet","display_name":"ResNet","score":0.7149999737739563},{"id":"https://openalex.org/keywords/early-language-development","display_name":"early childhood language development","score":0.7549999952316284},{"id":"https://openalex.org/keywords/teacher-child-interaction","display_name":"teacher-child interaction","score":0.5540000200271606}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7476578950881958},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5647115707397461},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5554154515266418},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5552772283554077},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5132687091827393},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.36794957518577576},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3202569782733917},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28791993856430054},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.2444857954978943},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000328","descriptor_name":"Adult","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D002675","descriptor_name":"Child, Preschool","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003142","descriptor_name":"Communication","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007804","descriptor_name":"Language Development","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013067","descriptor_name":"Speech Perception","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1121/10.0024353","doi":"https://doi.org/10.1121/10.0024353","is_oa":false,"landing_page_url":"https://doi.org/10.1121/10.0024353","pdf_url":null,"source":{"id":"https://openalex.org/S11296630","display_name":"The Journal of the Acoustical Society of America","issn_l":"0001-4966","issn":["0001-4966","1520-8524","1520-9024"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","ccf-b","cwts-core","dongbi-b","erih-plus","jufo-3","ki-jl-1","medline","norway-2","poland-100","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310320226","host_organization_name":"Acoustical Society of America","host_organization_lineage":["https://openalex.org/P4310320226"],"host_organization_lineage_names":["Acoustical Society of America"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Journal of the Acoustical Society of America","raw_type":"journal-article"},{"id":"pmid:38341746","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38341746","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Journal of the Acoustical Society of America","raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"id":"https://metadata.un.org/sdg/4","display_name":"Quality education"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G4925320186","display_name":"Collaborative Research: CSL-MultiAD: Assessing Collaborative STEM Learning through Rich Information Flow based on Multi-Sensor Audio Diarization","funder_award_id":"1918032","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320327708","display_name":"University of Texas at Dallas","ror":"https://ror.org/049emcs32"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W1528954144","https://openalex.org/W1556084866","https://openalex.org/W1556857061","https://openalex.org/W1821462560","https://openalex.org/W1936725236","https://openalex.org/W2023098317","https://openalex.org/W2069620976","https://openalex.org/W2150769028","https://openalex.org/W2189248916","https://openalex.org/W2194775991","https://openalex.org/W2407501792","https://openalex.org/W2512537248","https://openalex.org/W2525241666","https://openalex.org/W2587150483","https://openalex.org/W2727244960","https://openalex.org/W2807627734","https://openalex.org/W2889288729","https://openalex.org/W2889418727","https://openalex.org/W2890964092","https://openalex.org/W2916104401","https://openalex.org/W2936299888","https://openalex.org/W2937267585","https://openalex.org/W2954282963","https://openalex.org/W2968257153","https://openalex.org/W2972403660","https://openalex.org/W2973193289","https://openalex.org/W2973896964","https://openalex.org/W2979665226","https://openalex.org/W2981983183","https://openalex.org/W2995588677","https://openalex.org/W3006898571","https://openalex.org/W3010830830","https://openalex.org/W3012546915","https://openalex.org/W3024869864","https://openalex.org/W3025757635","https://openalex.org/W3031133340","https://openalex.org/W3034010994","https://openalex.org/W3034368386","https://openalex.org/W3036601975","https://openalex.org/W3090014957","https://openalex.org/W3093582452","https://openalex.org/W3097629653","https://openalex.org/W3128688470","https://openalex.org/W3130435173","https://openalex.org/W3130967494","https://openalex.org/W3135241621","https://openalex.org/W3141174088","https://openalex.org/W3143367551","https://openalex.org/W3157070662","https://openalex.org/W3160753639","https://openalex.org/W3202053206","https://openalex.org/W4200634095","https://openalex.org/W4225693939","https://openalex.org/W4311000453","https://openalex.org/W4385822293"],"related_works":["https://openalex.org/W4367276802","https://openalex.org/W4367022905","https://openalex.org/W3141174088","https://openalex.org/W4408353371","https://openalex.org/W3006898571","https://openalex.org/W4309321049","https://openalex.org/W4312459597","https://openalex.org/W7163215147","https://openalex.org/W2587126577","https://openalex.org/W7213706444"],"abstract_inverted_index":{"Speech":[0],"and":[1,10,25,38,57,176,240,245],"language":[2,21],"development":[3],"are":[4,43,66,197],"early":[5,76],"indicators":[6],"of":[7,59,69,75,84,128,166,179,226,242,263],"overall":[8],"analytical":[9],"learning":[11],"ability":[12],"in":[13,28,46,87],"children.":[14],"The":[15,221,247],"preschool":[16],"classroom":[17,78,126],"is":[18,183],"a":[19,163],"rich":[20],"environment":[22],"for":[23,106,124,199,213,255,258],"monitoring":[24],"ensuring":[26],"growth":[27],"young":[29],"children":[30,132,153,244],"by":[31],"measuring":[32],"their":[33],"vocal":[34],"interactions":[35,127],"with":[36,133,185,202,260],"teachers":[37,259],"classmates.":[39],"Early":[40],"childhood":[41,77],"researchers":[42],"naturally":[44],"interested":[45],"analyzing":[47],"naturalistic":[48,219],"vs":[49,208],"controlled":[50],"lab":[51],"recordings":[52],"to":[53,81,98,101,191],"measure":[54],"both":[55,238],"quality":[56],"quantity":[58],"such":[60,88],"interactions.":[61],"Unfortunately,":[62],"present-day":[63],"speech":[64,145,187],"technologies":[65],"not":[67],"capable":[68],"addressing":[70,227],"the":[71,82,138,224,261],"wide":[72],"dynamic":[73],"scenario":[74],"settings.":[79],"Due":[80],"diversity":[83],"acoustic":[85],"events/conditions":[86],"daylong":[89],"audio":[90,108,233],"streams,":[91],"automated":[92],"speaker":[93,204],"diarization":[94,122,142],"technology":[95],"would":[96],"need":[97],"be":[99],"advanced":[100],"address":[102],"this":[103,136],"challenging":[104],"domain":[105],"segmenting":[107,125],"as":[109,111,147],"well":[110],"information":[112],"extraction.":[113],"This":[114],"study":[115,222],"investigates":[116],"alternate":[117],"deep":[118],"learning-based":[119],"lightweight,":[120],"knowledge-distilled,":[121],"solutions":[123],"3-5":[129],"years":[130],"old":[131],"teachers.":[134],"In":[135],"context,":[137],"focus":[139],"on":[140,168,174,215],"speech-type":[141],"which":[143,210],"classifies":[144],"segments":[146,201],"being":[148],"either":[149],"from":[150,170],"adults":[151],"or":[152],"partitioned":[154],"across":[155],"multiple":[156],"classrooms.":[157],"Our":[158],"lightest":[159],"CNN":[160],"model":[161],"achieves":[162],"best":[164],"F1-score":[165],"\u223c76.0%":[167],"data":[169],"two":[171],"classrooms,":[172],"based":[173],"dev":[175],"test":[177],"sets":[178],"each":[180],"classroom.":[181],"It":[182],"utilized":[184],"automatic":[186],"recognition-based":[188],"re-segmentation":[189],"modules":[190],"perform":[192],"child-adult":[193],"diarization.":[194],"Additionally,":[195],"F1-scores":[196],"obtained":[198],"individual":[200],"corresponding":[203],"tags":[205],"(e.g.,":[206],"adult":[207],"child),":[209],"provide":[211],"knowledge":[212],"educators":[214],"child":[216,249],"engagement":[217],"through":[218,231],"communications.":[220],"demonstrates":[223],"prospects":[225],"educational":[228],"assessment":[229],"needs":[230],"communication":[232,250],"stream":[234],"analysis,":[235],"while":[236],"maintaining":[237],"security":[239],"privacy":[241],"all":[243],"adults.":[246],"resulting":[248],"metrics":[251],"have":[252],"been":[253],"used":[254],"broad-based":[256],"feedback":[257],"help":[262],"visualizations.":[264]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2024-02-12T00:00:00"}
